Journal of Theoretical and Applied Information Technology

Journal of Theoretical and Applied Information Technology
June 2016 | Vol. 88 No.3

Title:

A NEW SOFT SET BASED PRUNING ALGORITHM FOR ENSEMBLE METHOD

Author:

MOHD KHALID AWANG, MOKHAIRI MAKHTAR, M NORDIN A RAHMAN, MUSTAFA MAT DERIS

Abstract:

Ensemble methods have been introduced as a useful and effective solution to improve the performance of the classification. Despite having the ability of producing the highest classification accuracy, ensemble methods have suffered significantly from their large volume of base classifiers. Nevertheless, we could overcome this problem by pruning some of the classifiers in the ensemble repository. However, only a few researches focused on the ensemble pruning algorithm. Therefore, this paper aims to increase classification accuracy and at the same time minimizing ensemble classifiers by constructing a new ensemble pruning method (SSPM) based on dimensionality reduction in soft set theory. Ensemble pruning deals with the reduction of predictive models in order to improve its efficiency and predictive performance. Soft set theory has been proved to be an effective mathematical tool for dimension reduction. Thus, we proposed a novel soft set based method to prune the classifiers from heterogeneous ensemble committee and select the best subsets of the component classifiers prior to the combination process. The results show that the proposed method not only reduce the number of members of the ensemble, but able to produce highest prediction accuracy.

Keywords:

Ensemble Pruning, Ensemble Selection, Soft Set, Ensemble Methods

Source:

Journal of Theoretical and Applied Information Technology
30^th June 2016 -- Vol. 88. No. 3 -- 2016

Full Text

Title:	FACEBOOKS PUBLIC SOCIAL INTERACTION UTILIZATION TO ASSIST RECOMMENDATION ACROSS SYSTEM DOMAIN
Author:	MUHAMMAD MURAD KHAN, IMRAN GHANI, SEUNG RYUL JEONG, ROLIANA IBRAHIM , KASHIF NASEER QURESHI
Abstract:	Social media is most prominent internet transition for this decade and Facebook holds its largest share. Facebook has been utilized by researchers from different perspectives e.g. opinion mining, user mood swing pattern, influential person identification etc. whereas recently Facebooks social interactions were used for recommendation purposes. Although social interactions assisted recommendation, these interactions forced algorithm to work inside Facebooks ecosystem i.e. recommending items existing inside Facebook to Facebook users and these interactions were private in nature, requiring explicit permission from user before algorithm execution. This study utilize Facebooks public social interactions to recommend items across system domain i.e. recommending items to users existing outside Facebook. For this purpose we propose an algorithm that first identify items on Facebooks public pages, gather social interactions related to them, generate a rank list and finally recommend it to external users. As an experimental case study, whatmobile.pk Facebooks public social page was scanned for items and respective social interactions. These items were then compared with “fan” attribute of items existing on GSMARENA.com website in order to show rank similarity. 299 total items were found common between Facebooks public page and GSMARENA website. Items were ranked according to social interactions and “fans” quantity. Then a positive spearman correlation of 0.547 was found which was improved to 0.660 by excluding 22 mobile phones.
Keywords:	Facebook, Recommendation, Cross Domain, Rank Similarity, Public Social Interaction
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2016 -- Vol. 88. No. 3 -- 2016
Full Text

Title:	FACTORS AFFECTING THE ADOPTION OF ENTERPRISE RESOURCE PLANNING (ERP) ON CLOUD AMONG SMALL AND MEDIUM ENTERPRISES (SMES) IN PENANG, MALAYSIA
Author:	LEOW YI QIAN, AHMAD SUHAIMI BAHARUDIN, ABDULKARIM KANAAN-JEBNA
Abstract:	The purpose of this research is to investigate the effect of cloud security and data privacy, cost effectiveness, Internet reliability, top management support, and competitive pressure factors on the intention to adopt cloud-based ERP system by Small and Medium Enterprises (SMEs) in Penang, Malaysia. This study employs a survey method where 300 SMEs in both manufacturing and service sectors were selected from a list taken from the SME Corporation Malaysia (SME Corp) website. Statistical Package for Social Science (SPSS) version 20 was used to analyze the collected data. There were 51 valid data records from the manufacturing sector as well as 51 valid data responses from the service sector. This paper has developed a theoretical model using the Technological Organizational Environmental (TOE) framework and formulated several hypotheses. The results of this study have revealed that the top management support factor significantly and positively correlates with the intention to adopt cloud-based ERP system in manufacturing SMEs only. In addition, the analyses have found that all the factors have no significant impact on the intention to adopt cloud-based ERP system in both sectors. The practical contribution in this research will be the guidelines for cloud-based ERP providers, SMEs, as well as the Malaysian government in order to encourage the application of cloud-based ERP systems by SMEs.
Keywords:	Smes, ERP, Cloud Computing, Cloud-Based ERP System, Intention To Adopt, Cloud Security And Data Privacy, Cost Effectiveness, Internet Reliability, Top Management Support, And Competitive Pressure
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2016 -- Vol. 88. No. 3 -- 2016
Full Text

Title:	EFFICIENT THYROID DISEASE CLASSIFICATION USING DIFFERENTIAL EVOLUTION WITH SVM
Author:	K.GEETHA, CAPT. S. SANTHOSH BABOO
Abstract:	Thyroid diseases are widespread worldwide. In India too, there is a significant problems caused due to thyroid diseases. Various research studies estimates that about 42 million people in India suffer from thyroid diseases [4]. There are a number of possible thyroid diseases and disorders, including thyroiditis and thyroid cancer. This paper focuses on the classification of two of the most common thyroid disorders are hyperthyroidism and hypothyroidism among the public. The National Institutes of Health (NIH) states that about 1% of Americans suffer from Hyperthyroidism and about 5% suffer from Hypothyroidism. From the global perspective also the classification of thyroid plays a significant role. The conditions for the diagnosis of the disease are closely linked; they have several important differences that affect diagnosis and treatment. The data for this research work is collected from the UCI repository which undergoes preprocessing. The preprocessed data is multivariate in nature. Curse of Dimensionality is followed so that the available 21 attributes is optimized to 10 attributes using Hybrid Differential Evolution Kernel Based Navie Based algorithm. The subset of data is now supplied to Support Vector Machine (SVM) classifier algorithm where Radial Basis Function Kernal(RBF) is used. In order to stabilize the errors this iterative process takes 25 and the data is classified. The accuracy of classification is observed to be 99.89%. This result is efficient when compared to our previous work that used the Kernel based Naive bayes classifier.
Keywords:	Classification, Curse of Dimensionality, Differential Evolutionary algorithm, Multivariate Bayesian prediction, Radial Basis Function Kernel, Support Vector Machine, Thyroid disease, Wrapper model
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2016 -- Vol. 88. No. 3 -- 2016
Full Text

Title:	IMPLEMENTATION OF PACKING METHODS FOR THE ORTHOGONAL PACKING PROBLEMS
Author:	CHEKANIN VLADISLAV A., CHEKANIN ALEXANDER V
Abstract:	In the paper is considered a multidimensional orthogonal packing problem in general case. Are described packing methods developed for formation of placement schemes during solving the rectangular cutting and orthogonal packing problems of arbitrary dimensions. The presented packing model allows to describe all existing free spaces in containers. Are offered methods of placing and deleting of orthogonal objects, application of which in optimization packing algorithms will improve the quality of packing. Is described a new data structure providing increasing speed of packing formation. Efficiency of application of the packing methods is investigated on standard instances of three-dimensional orthogonal packing problems. All designed packing methods are realized in a form of an applied software which can be used in solving problems of resources allocation including container loading, cutting stock, scheduling, knapsack problems and many other practical important cutting and packing problems.
Keywords:	Packing, Orthogonal Packing Problem, Data Structure, Object-Oriented Programming, Applied Software
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2016 -- Vol. 88. No. 3 -- 2016
Full Text

Title:	ENRICH FRAMEWORK FOR MULTI-DOCUMENT SUMMARIZATION USING TEXT FEATURES AND FUZZY LOGIC
Author:	SACHIN PATIL, RAHUL JOSHI
Abstract:	The rapid growth of Information Technology triggers collection of documents in massive form, so to find the important information from multiple document is a complex task. The multiple documents summarization is task of producing assured summary from these document set. There are other summarization techniques like sentence clustering, term weight etc. However, these techniques use only two or three feature of text to find the importance of considered sentence. In this paper, we put forward an idea of text summarization which considers multiple extracted features by applying natural language processing (NLP) protocol. The ten feature of text are extracted and these feature classified on the basis of fuzzy logic to get the best documents summary. The key features are preprocessing, feature scoring, inference engine, and fuzzy logic.
Keywords:	Preprocessing, Feature Scoring, Normal Distribution, Inference Engine, Fuzzy Logic.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2016 -- Vol. 88. No. 3 -- 2016
Full Text

Title:	PREDICTION OF THE GROUP VELOCITY OF ACOUSTIC CIRCUMFERENTIAL WAVES BY ARTIFICIAL NEURAL NETWORK
Author:	YOUSSEF NAHRAOUI, EL HOUCEIN AASSIF, GERARD MAZ
Abstract:	The present study investigates the use an Artificial Neural Network (ANN) to predict the velocity dispersion curve of the antisymmetric (A1) circumferential waves propagating around an elastic cooper cylindrical shell of various radius ratio b/a (a: outer radius and b: inner radius) for an infinite length cylindrical shell excited perpendicularly to its axis. The group velocity is determined from the values calculated using the eigen mode theory of resonances. These data are used to train and to test the performances of this model. Levenberg-Marquaedt backpropagation training algorithm with tangent sigmoid transfer function and linear transfer function results in best model for prediction of group velocity. The overall regression coefficient, mean relative error (MRE), mean absolute error (MAE) and standard error (SE) are 1, 0.01%, 0.38 and 0.07. It is found that the neural networks are good tools for simulation and prediction of some parameters that carry most of the information available from the response of the shell. Such parameters may be found from the velocity dispersion of the circumferential waves, since it is directly related to the geometry and to the physical properties of the target.
Keywords:	Artificial Neural Network (ANN), Acoustic Response, Submerged Elastic Shell, Scattering Waves, Circumferential Waves, Phase Velocity, Group Velocity.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2016 -- Vol. 88. No. 3 -- 2016
Full Text

Title:	ANALYSIS STUDY OF A CASCADED H-BRIDGE MULTI-LEVEL INVERTER DEDICATED TO POWER BANK USAGE
Author:	TAJEDDINE KHALILI, ABDELHADI RAIHANI, OMAR BOUATTAN, HASSAN OUAJJI, FOUAD AMRI
Abstract:	Multi-level inverters have proved their efficiency for usage in variety of renewable energy applications. Therefore Converting DC voltage in a power bank containing multiple units using directly a multilevel inverter is a very powerful converting method. In this paper we present an analysis study of the cascaded H-bridge inverter in different conditions and different states namely 5, 9, and 17 levels. The architecture used trough the entire study is the same topology, the same command type was applied for all the models (SPWM). The study focuses on the output voltage quality and the efficiency of the power conversion. The study also discusses the influence of the unbalanced units state of charge inside the power bank on quality of the output voltage and present the most efficient level state configuration in both cases balanced and unbalanced.
Keywords:	Multilevel Inverter, Cascaded H-bridge, SPWM, Unbalanced DC, THD.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2016 -- Vol. 88. No. 3 -- 2016
Full Text

Title:	INFORMATION TECHNOLOGY FOR NUMERICAL SIMULATION OF VISCOUS INCOMPRESSIBLE FLOW IN BICONNECTED DOMAINS
Author:	NURLAN TEMIRBEKOV, SAYA TOKANOVA, YERZHAN MALGAZHDAROV
Abstract:	This paper analyzes the method of supplemented domains for the numerical simulation of viscous incompressible flow in the complex geometrical domain. The problem is considered in a discrete defined biconnected domain with the curved boundary. The spline interpolation of curved boundary is conducted. The Navier-Stokes equations for viscous incompressible fluid are selected for the numerical simulation. A stable finite-difference scheme and an algorithm of numerical implementation are developed. The numerical results are obtained with different numbers of grid nodes.
Keywords:	Navier-Stokes Equations, Viscous Incompressible Fluid, Numerical Simulation, Numerical Experiment, Stream Function, Method Of Supplemented Domains, Cube Spline Interpolation, Curvilinear Biconnected Domain.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2016 -- Vol. 88. No. 3 -- 2016
Full Text

Title:	IMPLEMENTATION OF IMPROVED LEVENSHTEIN ALGORITHM FOR SPELLING CORRECTION WORD CANDIDATE LIST GENERATION
Author:	HANAN NAJM ABDULKHUDHUR, IMAD QASIM HABEEB, YUHANIS YUSOF, SHAHRUL AZMI MOHD YUSOF
Abstract:	Candidates list generation in spelling correction is a process of finding words from a lexicon that are close to the incorrect word. The most widely used algorithm to generate the candidate list is the Levenshtein algorithm. However, the algorithm consumes high computational cost, especially when there is a large number of spelling errors. The reason is that calculating Levenshtein algorithm includes operations that create an array and fill the cells of this array by comparing the characters of an incorrect word with the characters of a word from a lexicon. Since most lexicons contain millions of words, such operations will be repeated millions of times for each incorrect word in order to generate its candidates list. This study proposes an improved Levenshtein algorithm that reduces the operation steps in comparing characters between the query and lexicon words. Experimental results show that the proposed algorithm outperformed the Levenshtein algorithm in terms of processing time by having 32.43% percentage decrease.
Keywords:	Levenshtein Algorithm, Processing Time, Word Candidate List Generation, Spelling Correction, Edit Distance
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2016 -- Vol. 88. No. 3 -- 2016
Full Text

Title:	A SNS-INTEGRATED COLLABORATIVE LEARNING SYSTEM TO SUPPORT PROGRAMMING LANGUAGE LEARNING
Author:	FANG-FANG CHUA, KEK-LUN LIEW
Abstract:	Today, using and accessing to Social Network Services (SNS) are part of our daily activities and have gained popularity to attract learners in the socialization engagement. This motivates the adoption of Social Network Services into collaborative learning environment which strongly encourage communication and interaction between learners. The engagement of learners to use the learning system is always a challenge to improve as they are easily distracted, lack of motivation and interest. The factors which contribute to the problems are mainly the availability of the learning resources, variety of the communication mode within the system, and also lack of real time interaction. With the implementation of Social Network Services (i.e. Facebook services and Twitter services) into collaborative learning environment, learners will feel motivated and engage more eagerly with the learning process as reflected from the heavy usage of social media recently. Real time communication and interaction are being promoted and learners can express and share real thoughts and feelings with the help of SNS while going through the learning process. In this proposed work, we design and implement a SNS-integrated collaborative learning system that allows learners to collaborate and learn anytime and anywhere. We have chosen the subject domain of learning programming language to realize our proposed solution.
Keywords:	Social Network Services, collaborative learning, Facebook, communication, collaboration, interaction
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2016 -- Vol. 88. No. 3 -- 2016
Full Text

Title:	SOCIAL NETWORK SITE (SNS) APPROPRIATION PROCESS IN FAMILY PERSPECTIVE BASED ON FAMILY TYPES
Author:	YUZI MAHMUD, NOR ZAIRAH AB. RAHIM, SURAYA MISKON
Abstract:	Many previous researchers have highlighted the positive and negative impacts of SNS usage in family environment such as improving family communications and bonding or worsen the family relationships. These impacts would varies depending on the family relationships. However, studies on SNS adoption, adaptation and use according to different types of family relationships have received little research attention. Eleven actual case studies which involved 31 respondents were selected. The data collection were conducted through interviews, observations and content analysis to achieve the main research objectives of why and how do family members adopt, adapt and use SNS according to different types of family groups. Results from the data collection were used in the development of Family Appropriation Process of Social Network Site (FAPSNS) framework which also facilitated in the understanding of SNS appropriation process criteria in family, individual, technical and extra-familial perspectives. The current level of SNS appropriation according to family groups namely Modern, Chummy and Mixed families are also identified. However, this paper is focusing on the SNS appropriation process in family perspective only. The results highlighted that Modern family has successfully appropriated Facebook at Level 3 of family perspectives. Whereas, Chummy and Mixed families have disappropriated Facebook at Level 2 in family perspective.
Keywords:	Facebook, Model of Technology Appropriation (MTA), Socio-Technical Theory, Family System Theory
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2016 -- Vol. 88. No. 3 -- 2016
Full Text

Title:	THE ANTECEDANTS OF BROADBAND INTERNET ADOPTION AND CONTINUANCE USAGE IN MALAYSIAN HOUSEHOLD CONTEXT
Author:	SARAVANAN NATHAN LURUDUSAMY, T. RAMAYAH
Abstract:	The Internet is simply a series of worldwide computer networks linked together, communicating almost instantly by using various access technologies. It is playing a major role in many areas of our lives, such as communication, entertainment and information which is supported by newer innovations and technology evolvement. While the broadband Internet penetration rate is encouraging in many countries, its adoption is still a notable issue in Malaysia. Therefore this research is focused on identification of two relevant research streams covering broadband Internet, which are adoption and continuance of usage (after initial adoption) in Malaysia. The theoretical framework which is utilized in this study is an integrated model of Unified Theory of Acceptance and Use of Technology (UTAUT) and IS- Continuance Model which has been further extended by integrating another 2 Independent Variables, namely Perceived Innovativeness and Perceived Playfulness. This study is trying to determine the relationship among the independent variables that influences the adoption and continuance usage of Broadband Internet technology among Malaysian individuals. Survey was used as the research instrument and the unit of analysis are existing broadband Internet subscribers in Malaysia. Data obtained from the survey was analyzed using Partial Least Square (PLS-SEM) and indicate that intention to adopt broadband have a significant positive influence on initial usage, Intention to continue using broadband have a significant positive influence on actual usage continuance and Initial broadband usage have a significant positive influence on usage continuance of broadband. This paper is concluded by some recommendations, limitations and directions for future study.
Keywords:	Internet Broadband, Technology Adoption, UTAUT, Continuance Usage Of Technology
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2016 -- Vol. 88. No. 3 -- 2016
Full Text

Title:	TOWARDS EXPLORING FACTORS THAT INFLUENCE SOCIAL MEDIA-BASED KNOWLEDGE SHARING INTENTIONS IN DISASTER MANAGEMENT
Author:	YUNIS ALI AHMED, MOHAMMAD NAZIR AHMAD, NOR HIDAYATI ZAKARIA
Abstract:	Knowledge sharing is considered vitally important for the success of disaster management initiatives. Within the process of disaster management, a growing number of users have started to utilize social media as a means of knowledge sharing. Specifically, social media empowers individuals to take part in knowledge sharing activities, which will in turn encourage more people to join in disaster relief activities. Encouraging online knowledge sharing behaviors among employees is a prominent research topic. However, to date, little empirical research has been undertaken to examine social media- based knowledge sharing behaviors within the disaster management domain. This study explores the factors that facilitate voluntary social media-based knowledge sharing intentions, for use within disaster management. The study offers a conceptual model for assessing these factors. In this paper, the three dependent variables of individual attitude, subject norms and perceived behavioral control are defined as related to social media-based knowledge sharing intention. In addition, the three groups of organizational factors, individual factors and technology factors, with seven subset variables of management support, organizational reward, knowledge self-efficacy, interpersonal trust, enjoyment in helping others, perceived usefulness and perceived ease of use, are identified as independent variables in this study. This study reviews the existing literature both in the field of social media-based knowledge sharing in general and in the disaster management domain in particular. Comparing this research with other studies, the main difference is that this study proposes a full set of factors that influence social media-based knowledge sharing behavior. Concluding remarks and suggestions for further statistical study work are provided, particularly in relation to the implications for disaster relief organizations in Somalia.
Keywords:	Knowledge Sharing, Social Media, Social Media-Based Knowledge Sharing, Disaster Management.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2016 -- Vol. 88. No. 3 -- 2016
Full Text

Title:	MULTI-PARTY PROTOCOL WITH ACCESS CONTROL ON SYMMETRIC FULLY HOMOMORPHIC ENCRYPTION SCHEME
Author:	WAMDA NAGMELDIN, SITI MARIYAM SHAMSUDDIN
Abstract:	Homomorphic encryption is a particular class of encryption presented by Rivest, Adleman et al. in 1978 that permits mathematical operations on the encrypted data without decrypting it [1], in fact, without knowing the decryption key. In the last few years, homomorphic encryption techniques have been studied deeply since they have become more and more vital and important in several different cryptographic applications such as lottery protocols, voting protocols, anonymity, privacy, and electronic auctions.This paper introduces the symmetric fully homomorphic scheme (Sym-FHE) and multi-party protocol with access control to allow many users access and manipulate the data in the cloud without violating the confidentiality of sensitive data.
Keywords:	Homomorphic Encryption, Cloud Computing, Multi-party.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2016 -- Vol. 88. No. 3 -- 2016
Full Text

Title:	HEALTH CARE ANALYSIS FOR PROCESS DEVIATION USING ALPHA-FITNESS ALGORITHM IN PROCESS MINING
Author:	GANESHA K, RASHMI NAGARAJ, NAYANA MD
Abstract:	Health care sectors are continuously exploring new and innovative way to improve operational efficiencies. This research study investigate a way to find potential efficiency gains in healthcare sectors by observing how they are carried out in the past and then investigating better ways of implementing them by considering the factors like time, cost and resource utilization. To achieve competitive advantage, healthcare centers try and contour their processes. Process mining can be enforced to extract data from recorded event. The aim of the system is to propose effective process models by applying dataset for each model which indeed identifies the deviation from the actual process with help the of analytical tool ProM. In this paper several blood tests are considered as the baseline scenario wherein effective process models are generated and checked for the efficiency using alpha-fitness algorithm. One of the major parts involved in process improvement is process modeling which can be optimized and analyzed.
Keywords:	Process Deviation, Event Log, Information Management Systems, Prom, Alpha.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2016 -- Vol. 88. No. 3 -- 2016
Full Text

Title:	THE IMPLEMENTATION OF INFORMATION TECHNOLOGIES IN HIGHER EDUCATION: A CASE OF KAZAKHSTAN AND TURKEY
Author:	MERUYERT TLEBALDIYEVA, TILEGEN SADIKOV, GULMIRA KAMIYEVA, ZULKIYA MOLDAKHMETOVA
Abstract:	The purpose of this research is to analyze the issues related to implementing information technologies into an educational system by the example of Turkey and Kazakhstan. Information technologies have been increasingly used in educational institutions for refining the quality of service and achieving the efficient organizational outcomes in the context of a competitive international environment. The integration of computer technologies into an educational system depends on its successful elaboration and application, which is an expensive and challenging process. This study also reveals the cooperation between Kazakhstan and Turkey in the sphere of information technologies and science. The results and recommendations can be applied in the educational, scientific and economic system development strategies and are of significant interest to Kazakh and Turkish scientific and educational thought.
Keywords:	Educational Technology, Information And Communication Technologies, Integration, Higher Education.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2016 -- Vol. 88. No. 3 -- 2016
Full Text

Title:	METHOD FOR STUDYING THE TUBULAR SOLAR COLLECTOR TESTING IN A LABORATORY
Author:	MURAT KUNELBAYEV, NURBAPA MEKEBAEYEV, ASSEM KABDOLDINA, ASHIRGUL SEIDILDAYEVA, DMITRY SERGEEVICH SILNOV
Abstract:	This paper considers the technique for studying the testing of tubular solar collector in a lab. Today, there are several ways methods of using solar collectors. When using the first method, the following values are measured: coolant flow, difference between the temperatures of the collector coolant fluid at the collector inlet and outlet and the density of the incident solar radiation flux. Here, all these values are measured simultaneously and under quasi-stationary mode. Much of the research is related to testing of collectors in field conditions using the instant method. At the end of the tests, the product of the total heat loss coefficient of the collector and efficiency coefficient of the absorption panel was determined. The heat output of the collector was also measured. As is seen from experimental methods of testing tubular solar collector, the tubular collector with an absorbing screen decreases from 0.8 to 0.17 when water is supplied at the inlet 20 C, 30 C, 40 C and 50 C, while the efficiency of the tubular collector with a reflector increases from 0.17 to 0.68 when water is supplied at the inlet 20 C, 30 C, 40 C, and then decreases to 0.4 at t1-50 C. It is obvious that the efficiency of heat absorption and transfer as a result of thermal conductivity is much higher than the capturing and reflection of sunlight by the absorbing pipe. However, both the cost and labor input involved in the manufacture of the above tubular collector with an absorbing screen is higher.
Keywords:	Tubular Solar Collectors, Heat Losses, Efficiency Factor, Optical Efficiency Product, Absorption Panel Efficiency Coefficient
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2016 -- Vol. 88. No. 3 -- 2016
Full Text

Title:	DESIGN OF SINGLE FEED CIRCULARLY POLARIZED HARMONIC SUPPRESSED MICRO STRIP PATCH ANTENNA FOR X-BAND APPLICATIONS
Author:	P.POORNA PRIYA, HABIBULLA KHAN, CH.ANUSHA, G.SAI TEJASWI, CH.SIVA RAMA KRISHNA
Abstract:	Introduction of a symmetrical slot near feed point for a symmetrical radiation patch of micro strip patch antenna realize both circular polarization and higher order mode suppression. Simulated and experimental results shows that application of symmetrical slot near feed point for asymmetrical patch can remarkably suppress the harmonic frequencies. Measured return loss and VSWR results shows that the proposed antenna suppress the higher order harmonics by maintaining circular polarization in X-band applications.
Keywords:	Circular Polarization, Harmonics Suppression, Micro Strip Antennas, Antenna Radiation Patterns
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2016 -- Vol. 88. No. 3 -- 2016
Full Text

Title:	EXTRACTION OF RETINAL BLOOD VESSEL USING ARTIFICIAL BEE-COLONY OPTIMIZATION
Author:	KAVYA K, DECHAMMA M.G, SANTHOSH KUMAR B.J
Abstract:	Retinal blood vessel Extraction in retinal images allows early diagnosis of disease and is useful in detecting ocular disorders and helps in laser surgery. Automating this process provides several benefits including minimizing subjectivity and eliminating a painstaking. This paper proposes an automated retinal blood vessel segmentation approach based on Fuzzy C-Means (FCM) clustering and then performed extraction using Artificial Bee-colony (ABC) to improve the accuracy of segmented image. FCM allocate the values of membership to the pixels instead of separating the pixels as in hard clustering problem and the clustering is optimized using ABC swarm based optimization algorithm, finally the system classify the images according to the level of damage in blood vessel using support vector machine (SVM). The performance was evaluated on DRIVE database and an accuracy of 96.35% was obtained.
Keywords:	Fundus Camera, Clustering, Fuzzy C-Means, Artificial Bee-Colony, Support Vector Machine.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2016 -- Vol. 88. No. 3 -- 2016
Full Text

Title:	THE EFFECT OF CIVIL CONFLICTS AND NET BENEFITS ON M-GOVERNMENT SUCCESS OF DEVELOPING COUNTRIES: A CASE STUDY OF IRAQ
Author:	SALIH HAJEM GLOOD, WAN ROZAINI SHIEK OSMAN, MASLINDA MOHD NADZIR
Abstract:	Information and communication technologies (ICTs) are playing an important role in the advancement of society. ICTs served as one of the main resources for promoting products and services, for delivering and broadcasting information, and also for connecting organizations and communities together in terms of better interaction and better communicational possibilities. Therefore, several governments seeking to establish IS projects by exploiting the modern of ICTs. The mobile government (mG) system is one of the important IS projects provided by governments to improve the quality of life, through enhancing the delivery of information or services to citizens. The ratio of use of mG services in developing countries, especially in rural areas, is still quite low and Iraq is not an exception. Despite of Iraq is the highest mobile penetration rate amongst 34 countries, the use of mG services amongst citizens in Iraq is lower than expected compared to the amount of money spent on this projects. Moreover, providing mobile government (mG) services alone did not guarantee success of mG without releasing the benefits of using mG services, especially in rural areas. Net benefits are considered a critical phenomenon for the success of any IS, and mG is not far from this issue. Thus, this study aims to investigate the contributing factors mG success in the Iraqi context, where literature in this field of research is lacking. Quantitative data were collected from Iraqi citizens in rural areas. Structural equation modeling was used to test the relationships between constructs. Results show that information quality has appositive effect on the use of mG, whereas the use of mG has a strong effect on net benefits of mG services. The moderating effect of civil conflicts between the use and net benefits of mG is supported negatively. The results imply that service providers need to deliver quality information and quality service to facilitate the users post-adoption usage of mG services under stable environment.
Keywords:	Civil Conflicts, Mobile Government, Net Benefits, Rural Areas, Evaluation IS Success
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2016 -- Vol. 88. No. 3 -- 2016
Full Text

Title:	SECURING DATA STORED IN CLOUDS USING MULTI KEYS AND PROXY INJECTION SCHEMES
Author:	GIRISHMA.V, Dr. K.V.V. SATYANARAYANA
Abstract:	A new robust control scheme for Multi key distribution scheme that supports secured data storage and access in clouds along with anonymous upload feature to protect user privacy is proposed.User authenticity is established by the cloud through proper registration procedures and in turn data authenticity with multi key sharing authenticity and support for anonymous sharing is established by registered users. Access control is being implemented where the stored information can be decrypted by users who are valid.Replay attacks are prevented through Proxy injection based schemes and they are also helpful in containing Cloud Services Provider (CSP) from knowing where-about of uploader themselves. User revocation is addressed and creating, reading and modifying information in cloud is also supported.
Keywords:	Cloud Data, Attribute Based Encryption, Anonymity Based Uploads and Key Distributions
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2016 -- Vol. 88. No. 3 -- 2016
Full Text

Title:	COMPARING WINDOWING METHODS ON FINITE IMPULSE RESPONSE (FIR) FILTER ALGORITHM IN ELECTROENCEPHALOGRAPHY (EEG) DATA PROCESSING
Author:	NOVA EKA DIANA, UMI KALSUM, AHMAD SABIQ, WISNU JATMIKO, PETRUS MURSANTO
Abstract:	Electroencephalography (EEG) data contains electric signal activities on a cerebral cortex to record brain electrical activities. EEG signal has some characteristics such as non-periodic, non-standardized pattern, and small voltage amplitude. Hence, it is lightly heaped up to noise and difficult to recognize and extract meaningful information from EEG data. Finite Impulse Response (FIR) with various windowing methods has been widely used to mitigate noise and distortions. This paper compares and analyzes the windowing techniques in resulting the most optimal results in EEG filtration process. The experiment results show that Blackman Window gives the best result in term of the most negative value in stop-band attenuation, the widest transition bandwidth, and the highest cutoff frequency compares to Rectangular Window, Hamming Window, and Hann Window.
Keywords:	Electroencephalography (EEG), Finite Impulse Response, Windowing Methods, Signal Filtering, Blackman Window
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2016 -- Vol. 88. No. 3 -- 2016
Full Text

Title:	A MACHINE LEARNING APPROACH FOR IDENTIFYING DISEASE TREATMENT RELATIONS IN SHORT TEXTS
Author:	T.V.M. SAIRAM, DR. G. RAMA KRISHNA
Abstract:	The Machine learning (ML) region has proved its power in almost every industry and is currently a reliable technology in health care industry. Computerized study of the clinical industry includes suitable care choice guide, healthcare photo and DNA connections. ML is recognized as a tool employing computer systems integrating health care mechanisms resulting in more appropriate care and attention patients and further study or research on a disease. This paper provides powerful algorithms and techniques used in diagnosing illness using remedy associated phrases from brief published written text launched in health-care documents. The objective of this work is to show how Natural Language Processing (NLP) and Machine Learning strategies can be used for reflection of information and what class strategies are appropriate for determining & figuring out suitable care information in brief published written textual content. This paper additionally focuses on suitable care analysis therapy & prevention of contamination, infection harm in human. The system found out some assignment of clinical suitable care statistics, health-care control, and man or woman health data and so forth. The proposed method may be incorporated with any health-care management software to make better suitable care selection. The inpatient management application can instantly mine bio-medical data from virtual databases.
Keywords:	Health-Care, System Mastering, Natural Language Processing, Aid Vector Machine, Choice Aid System.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2016 -- Vol. 88. No. 3 -- 2016
Full Text

Title:	INDIAN SIGN LANGUAGE RECOGNITION SYSTEM USING NEW FUSION BASED EDGE OPERATOR
Author:	M. V. D. Prasad, P. V. V. Kishore, E. Kiran Kumar, D. Anil Kumar
Abstract:	The objective is to generate a basis for sign language recognizer under simple backgrounds. Complications arise in extracting shapes of hands and head using traditional segmentation models due to non-uniform lighting. This paper proposes a wavelet based fusion of two weak edge detection models. One is morphological subtraction model and the other is gradient based canny edge operator. Elliptical Fourier descriptors provide shape models with optimized number of shape descriptors. Principle components determined keep the feature vector to a minimum to accommodate all the frames in the video sequence. Classification of the signs is achieved by training a neural network trained with back propagation algorithm. The proposed method is exclusively tested many times with different examples for correct recognition sequence. Finally, the recognition rate stands at 92.34% when compared to similar model using discrete cosine transform based features at 81.48%.
Keywords:	Artificial Neural Network (ANN), Canny Segmentation, Elliptical Fourier Descriptors, Morphology Segmentation, Principle Component Analysis.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2016 -- Vol. 88. No. 3 -- 2016
Full Text

Title:	LEXICAL BASED METHOD FOR PHISHING URLS DETECTION
Author:	AMMAR YAHYA DAEEF, R. BADLISHAH AHMAD, YASMIN YACOB
Abstract:	Phishing is a social engineering attack that exploits users ignorance during system processing has an impact on commercial and banking sectors. Numerous techniques are developed in the last years to detect phishing attacks such as authentication, security toolbars, blacklists, phishing emails, phishing websites, and URL analysis. Regrettably, nowadays detection system implemented for specific attack vectors such as email which make developing wide scope detection is much needed. Previous studies show that analysis of URLs proved to be a good option to detect malicious activities where this method mostly based on features of lexical, host information, and other complex method which requires a long processing time. In this paper, we present phishing detection system using features extracted from URLs lexical only to meet two important goals which are wide scope of protection and applicability in a real-time system. The system provides accuracy of 94% and can classify single URL in average time of 0.12 second.
Keywords:	Phishing, Classifiers, Machine Learning, Lexical Features.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2016 -- Vol. 88. No. 3 -- 2016
Full Text

Title:	ERHR-EFFICIENT AND RELIABLE HETEROGENEOUS ROUTING PROTOCOL FOR SENSOR NETWORKS
Author:	THOTA SIVA RATNA SAI, DR. SRIKANTHVEMURI
Abstract:	A WSN is a collection of various nodes having the capability to sense the information namely sensor nodes and organized over a distributed region, in that region all nodes are communicated with each other and forms the sensor network. The nodes of sensor network have limited communication interface, resources and computational resources. Moreover, sensor network are used in real life application. Mainly, each application requires different capabilities of sensor devices such as capability of sensing and range of propagation. Consequently, heterogeneous sensor networks are came into existence. Previously, various routing protocols are exist but most of them are concentrating on single issue. Those are data-centric, hierarchical, location based and quality of service. In this article we intend a new routing protocol it will address the heterogeneity of nodes and QOS issues. This protocol is implemented with NS2 and performance of the protocol is compared with standard sensor routing protocol AODV.
Keywords:	Heterogeneous wireless sensor networks, Routing, Wireless, Data-Centric, Hierarchical.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2016 -- Vol. 88. No. 3 -- 2016
Full Text

Title:	A DECISION SUPPORT SYSTEM FOR PREDICTING DIABETIC RETINOPATHY USING NEURAL NETWORKS
Author:	K CHANDANA, DR.Y.PRASANTH, J.PRABHU DAS
Abstract:	Diabetic retinopathy (DR) is an eye fixed ill complete by the impairment of polygenic disorder and that we purchased to acknowledge it before of calendar for sensible treatment. As polygenic disorder advances, the vision of a patient might begin to interrupt down and incite diabetic retinopathy. on these lines, 2 social occasions were perceived, specifically non-proliferative diabetic retinopathy (NPDR) , proliferative diabetic retinopathy (PDR).during this paper, to dissect diabetic retinopathy, 3 models like Probabilistic Neural framework (PNN), Bayesian Classification and Support vector machine (SVM) square measure pictured and their displays square measure thought-about. The live of the unwellness unfold within the membrane are often recognized by analytic the elements of the membrane. The elements like veins, hemorrhages of NPDR image and exudates of PDR image square measure off from the unrefined photos victimization the icon prepare techniques, fed to the classifier for gathering. a complete of 350 structure photos were used, out of that100 were used for designing and 250 pictures were used for testing. Exploratory results show that PNN has an accuracy of 89.6 % Bayes Classifier incorporates a exactness of 94.4% and SVM has an exactitude of 97.6%. This determines the SVM model beats one other model. What is more our system is equally continue running on 130 pictures open from "DIARETDB0: Evaluation Database and Procedure for Diabetic Retinopathy" and also the results show that PNN incorporates a exactness of 87.69% Bayes Classifier has an accuracy of 90.76% and SVM has a precision of 95.38%.
Keywords:	Probabilistic Neural Network Bayesian Classification, Support Vector Machine, Sensitivity, Specificity, Accuracy
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2016 -- Vol. 88. No. 3 -- 2016
Full Text

Title:	RECOGNIZING GENDER THROUGH FACIAL IMAGE USING SUPPORT VECTOR MACHINE
Author:	FITRI DAMAYANTI, AERI RACHMAD
Abstract:	The face is one part of the human body that has special characteristics, which is often used to distinguish the identity of one individual and another. Facial recognition is very important to be developed since this application is applied in the security system. The recognition of sex is one part of the face recognition. Gender plays an important role in our interactions in the community and with the computer. Classification gender of the face image can be applied in the field of demographic data collection, human-computer interface (customize the behavior of software in connection with the sex of the user) and others. The purpose of this study is to make implementation of the system in recognizing the gender on facial image or filling the form with the Gender Recognition face image that is able to recognize a person s sex quickly and accurately, and run well. This study used methods of Two Dimensional Linear Discriminant Analysis (TDLDA) for feature extraction, which directly assess within-class scatter matrix of the transformation matrix without any image into a vector image, and this resolves the singular problem within-class scatter matrix. To obtain optimal recognition results of the classification method, it used the classification Support Vector Machine. This study integrates TDLDA and SVM methods for the introduction of gender based on facial image. The combination of both methods proves the optimal results with an accuracy of 74% to 92% with a test that uses a database of faces taken from http://www.advancedsourcecode.com.
Keywords:	Support Vector Machine, Two Dimensional Linear Discriminant Analysis, Gender
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2016 -- Vol. 88. No. 3 -- 2016
Full Text

Title:	HUMAN EMOTION DETECTION THROUGH FACIAL EXPRESSIONS
Author:	KRISHNA MOHAN KUDIRI, ABAS MD SAID, M YUNUS NAYAN
Abstract:	Human to human social communication in real-life is possible through different modalities like facial expressions, speech and body poses. However, facial expressions plays important role while dealing with human emotions in real-life than the other modalities. It is because facial expression provides non-verbal data towards emotions. And also gives emotion of a person towards his goal. On the other hand, speech and body poses are mostly language and culture dependent respectively which creates problem while detection emotions of a person. Thus in order to deal with the above issues, this research work focused on facial expressions instead other modalities. To improve detection performance of the system, proposed Relative Sub-Image Based features is used. Support Vector Machine with radial basis kernel is used for classification. Total six basic emotions (angry, sad, happy, disgust, boredom and surprise) are tested. From experimental results, the proposed Relative Sub-Image Based features enhanced the classification rates than the conventional features.
Keywords:	Relative Sub-Image Based (RSB), Support Vector Machine (SVM), Human Computer Interaction (HCI).
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2016 -- Vol. 88. No. 3 -- 2016
Full Text

Title:	AN APPROACH FOR EFFICIENT AND SECURE COOPERATIVE WIRELESS NETWORKS USING TRANSMISSION RELIABILITY PROTOCOL
Author:	APOORVA P, NAGARJUN S, PARVATHI T V
Abstract:	Energy efficiency and security is the major problems identified in wireless sensor networks. This work introduces the Secured Cooperative communication protocol in wireless sensor networks for establishment of cooperative clusters during transmission of data in a collective way. In the cooperation process using cooperative transmission protocol, recruitment policy helps the nodes to co-operate each other. Cluster head on one node thick path recruit neighbouring nodes to assist in communication. Proposed method aimed to build security between the intermediate cluster nodes and also minimize the overall energy consumption and increase the transmission reliability of packet delivery between a source and a sink in an unreliable wireless network by giving some level of cooperation among them. Cooperative Transmission Protocol that uses any wireless networks communications between any source node and sink node can be with optimal energy and not compromising with the reliability of transmission to decrease packet loss. In order to bring the security among the nodes inside the cluster the method called Rijndael algorithm is used as an Advanced Encryption Standard (AES). AES provides flexibility and security between the systems when compared with other cryptographic algorithms. To enhance efficiency of sensors, the existing algorithm found inefficient. Hence with all accounting of the existing systems, this work concentrates on reducing energy consumption by selecting only few/optimal node and also maintains a data cache until an acknowledgement is received from receiving cluster head upon successful transmission.
Keywords:	Rijndael Algorithm, Rijndael Managed Objects (RMO), Crypto Stream Object, Cooperative Transmission, Salt Data, Initialization Vector(IV), Cooperative Caching.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2016 -- Vol. 88. No. 3 -- 2016
Full Text

Title:	EXTRACTION AND PROCESSING OF SITUATION SPATIOTEMPORAL TRAFFIC USING SVM ALGORITHM WITH BIG DATA
Author:	S HEMA LATHA, K SUBRAHMANYAM
Abstract:	With the wide variety of motion sensors that traffic information can come from many research has been reserved for the development of traffic forecast, which in turn increases the shipping routes, traffic management, urban planning, etc. The most important challenge is to predict how traffic based on predictive models based on historical data traffic in real time, which may differ from historical data and change over time. In this system can learn new context of the current online traffic situation (or context) in real time, most effectively formed using a predictive historical data traffic model is intended to predict the future of the current situation. If traffic in real time, distributed environment enters the bloodstream space efficiently adapt to assess the effectiveness of each significant predictor different situations. We can show you the way, and short-term and long-term performance guarantees (STEP), our algorithm is designed in accordance with the algorithm works well in situations where there are no real signs (for ex. Traffic Ready) or later. We proposed an algorithm called Extraction and Processing of situation Spatiotemporal traffic using SVM algorithm with Big data By using the proposed framework, a context in which the most important is to predict the traffic by monitoring the movement of vehicles, which can further reduce the complexity of the request and inform the trade-policy. Our experience with real data in real-time circumstances indicates that the proposed approach is superior to existing solutions.
Keywords:	Big data, Spatiotemporal, GPS, Traffic.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2016 -- Vol. 88. No. 3 -- 2016
Full Text

Title:	DIAGNOSIS OF HEART DISEASE USING NEURAL NETWORKS-COMPARATIVE STUDY OF BAYESIAN REGULARIZATION WITH MULTIPLE REGRESSION MODEL
Author:	K.SAI KRISHNASREE, M.R.NARASINGA RAO
Abstract:	Heart disease is one of the significant reasons of death and the progress of which is rampant all over the globe. Blood vessels carry blood with oxygen to all the cells in the body. It is a common reason that, Cholesterol and other substances can be deposited in blood vessels which block blood vessels and that no blood and oxygen can get to heart. This leads to heart disease. Several works have been made to predict the heart disease in different methods. The main aim of this paper is to predict heart disease using Multiple Regression and Bayesian Regularization methods and compare the results of these models. Multiple Regression is one of the strong model used for prediction and it shows the association between input variables and output variable. It predicts the output variable based on the relationship between one or more input variables and target variable. Bayesian regularization is a statistical model which process nonlinear dataset. It increases the generalization capability and decreases squared errors. Bayesian regularization works on with large inputs efficiently. The results are calculated using Multiple Regression and Bayesian Regularization methods and predicted the heart disease. The results of Multiple Regression and Bayesian Regularization are compared and it is observed that the results generated from Bayesian Regularization are more accurate than multiple regression model.
Keywords:	Bayesian Regularization, Multiple regression, Heart disease, Artificial Neural Network (ANN), Prediction.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2016 -- Vol. 88. No. 3 -- 2016
Full Text

Title:	FUSION OF COLOR AND STATISTIC FEATURES FOR ENHANCING CONTENT-BASED IMAGE RETRIEVAL SYSTEMS
Author:	AHMAD B. A. HASSANAT, AHMAD S. TARAWNEH
Abstract:	Content-based image retrieval is one of most debated topics in computer vision research, and has received a great deal of interest recently. It aims to retrieve similar images from a huge unlabelled image database. In this work we propose a method that reduces the error rate and retrieves relevant images early in the process, with the ability to work on both color and grayscale images. The proposed method scans an image using 8x8 overlapping blocks, extracting a set of probability density functions of the most discriminative statistical features. Our experiments, conducted on several image databases, show the robustness of the proposed method, outperforming some of the most popular methods described in the literature.
Keywords:	CBIR, Color Features, Statistical Features, Image Analysis, Computer Vision, Face Searching
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2016 -- Vol. 88. No. 3 -- 2016
Full Text

Title:	MORPH- SYNTACTIC ANALYSIS OF ARABIC WORDS BY DETERMINISTIC FINITE AUTOMATON (DFA)
Author:	HAMMAD BALLAOUI, EL HABIB BEN LAHMAR, NASSER LABANI
Abstract:	In this article we introduce a technical analysis that permits; on the one hand, to help the user to discriminate optimally the morphological results of a word in an Arabic text and to identify its nature (noun or a verb) on the basis of these prefixes, suffixes and its particles of attributions. On the other hand, we can determine the syntactic results of each analyzed word on the basis of the context. In this humble work, the approach has two steps: In the first stage, the study focuses on a broad analysis of words on the basis of Arabic rules. Then, in the second stage, we can clarify a technique based on a deterministic finite automaton (DFA), which is designed to treat the chosen words character by character in the sense of a suitable transition. In the final output and via different labels, the system determines the nature, the gender and number for each automated word.
Keywords:	Arabic Language, Automatic Natural Language Processing, Deterministic Finite Automaton (DFA), Disambiguation, Labeling, Morph-syntactic Analysis.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2016 -- Vol. 88. No. 3 -- 2016
Full Text

Welcome to Journal of Theoretical and Applied Information Technology